Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses behavior the annotations cannot: this is a two-phase PROPOSED write that returns status='confirmation_required' with action_id and plan_token and commits only through confirm_action. It also states side effects (reminders anchored to a moved occurrence follow it) and preservation semantics (each occurrence keeps its own duration and weekday), which is exactly the kind of context destructiveHint=true does not convey on its own.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core verb and the required-parameter caveat, then grouped logically by identifier requirements, move mechanics, and confirmation protocol. Dense but nearly every sentence carries operational meaning; the CONFIRMATION block is capitalized in a way that reads slightly like emphasis styling rather than prose, a minor structural blemish.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter destructive mutation with no output schema and no schema descriptions, the definition covers the pieces an agent could otherwise get wrong: scope semantics, ID requirements, move vs absolute-time rules, and the deferred-write contract. It does not say which fields are valid across which scopes (e.g. whether title/location apply to 'following'), leaving one genuine ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage the description must carry the load, and it does for the non-obvious parameters: scope is flagged REQUIRED with all three values defined, event_id vs series_id requirements are spelled out per scope, shift_minutes explains its non-obvious preservation behavior, and start_at's restriction is justified. The descriptive fields (title, location, notes, event_type, availability) get no coverage, but their names and the enum are largely self-explanatory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource ('Edit a repeating event') and immediately narrows the domain to recurring-series edits via the scope enum. It does not distinguish itself from the sibling 'update_event', so an agent must infer that this one handles repeating events while the other does not.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Strong explicit guidance on selection: which scope value applies to which intent, which identifier each scope requires, and the rule that start_at is only legal with scope='this' while shift_minutes is the tool for multi-occurrence moves. It stops short of naming the alternative tool to use for non-repeating events or for confirming the proposal (confirm_action is mentioned, so only the first is a real gap).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.